发表机构
New York University Abu Dhabi; NYUAD Research Institute; University of Coimbra（纽约大学阿布扎比分校; 纽约大学阿布扎比研究所; 科英布拉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究探讨能否将量子硬件物理噪声用作光子混合量子 - 经典神经网络的正则化器，借助模拟器和框架构建网络并注入噪声模型，用遗传算法搜索参数，结果表明噪声在部分数据集提升准确率，部分下降，其正则化效果因数据集而异。
AI 中文摘要
近期量子硬件中的物理噪声通常被视为需抑制的麻烦。我们探讨它能否作为光子混合量子 - 经典神经网络（PHQCNNs）的硬件天然正则化器，类似于经典深度学习中的噪声注入正则化。使用Quandela的Perceval模拟器和MerLin框架，构建用于鸢尾花、数字和MNIST的PHQCNNs并直接将Perceval的七参数物理噪声模型注入训练。通过遗传算法搜索六个连续噪声维度和一个布尔参数以找到每个数据集使验证准确率最大化的配置，并与无噪声基线对比。GA调整后的噪声在鸢尾花数据集上使准确率适度提高（+0.82个百分点），在数字数据集上提高（+1.45个百分点），但在MNIST数据集上明显下降（-1.21个百分点）。逐参数扫描表明没有单个噪声参数始终有益，这促使进行联合搜索，而二阶损失展开表明物理噪声会诱导一个类似蒂洪诺夫的正则化项，其效果取决于数据集。因此，物理光子噪声可作为免费正则化器，但并非普遍适用。
英文摘要
Physical noise in near-term quantum hardware is usually treated as a nuisance to suppress. We ask whether it can instead act as a hardware-native regularizer for photonic hybrid quantum-classical neural networks (PHQCNNs), analogous to noise-injection regularization in classical deep learning. Using Quandela's Perceval simulator and the MerLin framework, we build PHQCNNs for Iris, Digits, and MNIST and inject Perceval's seven-parameter physical noise model directly into training. A genetic algorithm searches the six continuous noise dimensions and 1 boolean parameter to find, per dataset, the configuration maximizing validation accuracy, compared against a noiseless baseline across five seeds. GA-tuned noise yields modest accuracy gains on Iris (+0.82pp) and Digits (+1.45pp), but a clear degradation on MNIST (-1.21pp). Per-parameter sweeps show that no individual noise parameter is consistently beneficial, motivating the joint search, while a second-order loss expansion shows that physical noise induces a Tikhonov-like regularization term whose effect is dataset-dependent. Physical photonic noise can thus act as a free regularizer, but not universally.
CommentsAccepted at the IEEE International Conference on Quantum Computing and Engineering (QCE), 2026
